{"slug":"aperivue-model-validation","source_name":"aperivue/model-validation","name":"Aperivue/Model Validation","description":"Design or audit the clinical-validation study for an engineer-built medical-imaging model (segmentation, classification, or detection) before the validation report or manuscript is written. Covers patient-level split disjointness and the data-leakage taxonomy, tuning-on-test, internal versus genuine external validation, comparator design, single-run versus multi-seed variance, task-correct metric selection, test-set sizing, and CLAIM 2024 / TRIPOD+AI / STARD-AI reporting fit. Ships a determinist","version":2,"lift":{"pass_rate_delta_pts":34.78,"pass_rate_pct":91.3,"total_cases":23,"passed_cases":21,"tokens_delta_pct":67.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-24T22:36:26.592235+00:00"},"skill_score":0.913,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":34.78,"with_pass_pct":91.3,"without_pass_pct":56.5,"tokens_delta_pct":67.6,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-24T22:36:26.592235+00:00","run_id":"4d52014c-df30-40b0-993e-c6696cdbcc85","version_number":2,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"d8e2efb4564559cf728d144fbafe838230973f811b42272ac8d43359246d623a","raw_url":"https://app.decimal.ai/s/aperivue-model-validation/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/aperivue-model-validation"}